Related papers: Exploring Simple Siamese Representation Learning
This paper introduces contrastive siamese (c-siam) network, an architecture for leveraging unlabeled acoustic data in speech recognition. c-siam is the first network that extracts high-level linguistic information from speech by matching…
Vision-Language Models (VLMs) rely heavily on pretrained vision encoders to support downstream tasks such as image captioning, visual question answering, and zero-shot classification. Despite their strong performance, these encoders remain…
Supervised contrastive learning (SupCL) has emerged as a prominent approach in representation learning, leveraging both supervised and self-supervised losses. However, achieving an optimal balance between these losses is challenging;…
Traditional audio-visual methods rely on independent audio and visual backbones, which is costly and not scalable. In this work, we investigate using an audio-visual siamese network (AVSiam) for efficient and scalable audio-visual…
A significant proportion of patients scanned in a clinical setting have follow-up scans. We show in this work that such longitudinal scans alone can be used as a form of 'free' self-supervision for training a deep network. We demonstrate…
Crowd segmentation is a fundamental task serving as the basis of crowded scene analysis, and it is highly desirable to obtain refined pixel-level segmentation maps. However, it remains a challenging problem, as existing approaches either…
This paper presents SimMIM, a simple framework for masked image modeling. We simplify recently proposed related approaches without special designs such as block-wise masking and tokenization via discrete VAE or clustering. To study what let…
Deep learning has proven itself as a successful set of models for learning useful semantic representations of data. These, however, are mostly implicitly learned as part of a classification task. In this paper we propose the triplet network…
Siamese networks are one of the most trending methods to achieve self-supervised visual representation learning (SSL). Since hand labeling is costly, SSL can play a crucial part by allowing deep learning to train on large unlabeled…
We study the problem of building text classifiers with little or no training data, commonly known as zero and few-shot text classification. In recent years, an approach based on neural textual entailment models has been found to give strong…
The objective of this paper is to address the localization problem using omnidirectional images captured by a catadioptric vision system mounted on the robot. For this purpose, we explore the potential of Siamese Neural Networks for…
In this paper, we tackle a fully unsupervised super-resolution problem, i.e., neither paired images nor ground truth HR images. We assume that low resolution (LR) images are relatively easy to collect compared to high resolution (HR)…
Recent work has made significant progress in learning object meshes with weak supervision. Soft Rasterization methods have achieved accurate 3D reconstruction from 2D images with viewpoint supervision only. In this work, we further reduce…
Network representation learning, as an approach to learn low dimensional representations of vertices, has attracted considerable research attention recently. It has been proven extremely useful in many machine learning tasks over large…
Continual Learning aims to bring machine learning into a more realistic scenario, where tasks are learned sequentially and the i.i.d. assumption is not preserved. Although this setting is natural for biological systems, it proves very…
Matching pedestrians across multiple camera views, known as human re-identification, is a challenging research problem that has numerous applications in visual surveillance. With the resurgence of Convolutional Neural Networks (CNNs),…
Different from image inpainting, image outpainting has relative less context in the image center to capture and more content at the image border to predict. Therefore, classical encoder-decoder pipeline of existing methods may not predict…
Inverse problems in image reconstruction are fundamentally complicated by unknown noise properties. Classical iterative deconvolution approaches amplify noise and require careful parameter selection for an optimal trade-off between…
It has been demonstrated that artificial neural networks like autoencoders or Siamese networks encode meaningful concepts in their latent spaces. However, there does not exist a comprehensive framework for retrieving this information in a…
Unsupervised learning permits the development of algorithms that are able to adapt to a variety of different data sets using the same underlying rules thanks to the autonomous discovery of discriminating features during training. Recently,…